Erbrechen Prävention bei Krebskrebs
Prävention des Erbrechens in pädiatrischen Onkologiestation unter Verwendung maschineller Lernen
The goal of this single arm trial is to learn if a machine learning (ML) model predicting the risk of vomiting within the next 96 hours will impact vomiting outcomes in inpatient cancer pediatric patients.
The main questions it aims to answer are whether an ML model predicting the risk of vomiting within the next 96 hours will:
Primary
1. Reduce the proportion with any vomiting within the 96-hour window
Secondary
- Reduce the number of vomiting episodes
- Increase the proportion receiving care pathway-consistent care
- Impact on specific antiemetic medication administrations
Exploratory: To determine whether deployment of the ML model reduces the proportion of patients with any nausea within 96 hours and to characterize references to the algorithm in clinical notes following deployment, and to determine the number of times the prediction report dashboard was opened.
Newly admitted participants will have a ML model predict the risk of vomiting within the next 96 hours according to their medical admission information. The prediction will be made at 8:30 AM following admission. Pharmacists will be charged with bringing information about patients' vomiting risk to the attention of the medical team and implementing interventions.
Studienübersicht
Status
Intervention / Behandlung
Detaillierte Beschreibung
Vomiting is one of the most common complications of cancer therapies in pediatric patients, with substantial negative impacts on quality of life. Vomiting can also reduce oral intake, worsen nutritional status and lead to hospitalization. Thus, efforts to control vomiting are crucial. The ability to predict which patients are most likely to vomit is limited; machine learning (ML) is a promising approach. Preliminary work completed for this study includes development of an enterprise data warehouse sourced from Epic suitable for ML named SickKids Enterprise-wide Data in Azure Repository (SEDAR) and validation of vomiting outcomes in SEDAR. Next, a standardized process for model training, evaluation and deployment was conducted by the study team. This was implemented to train a retrospective model to predict vomiting (0-96 hours post prediction time), which demonstrated satisfactory performance during a prospective silent trial. The care pathway and patient-specific report to facilitate clinical care based on a positive prediction has also been created by the study team, expending on a previously developed antiemetic care pathway based on clinical practice guidelines. The patient-specific report lists each patient's risk of vomiting (0-96 hours post prediction time), vomiting prior to prediction time, planned chemotherapy or procedures, current antiemetic orders and history of vomiting with the most recent admission.
For model deployment, pharmacists will be charged with bringing information about patients' vomiting risk to the attention of the medical team and implementing care pathway-consistent interventions. Pharmacists will receive a list of high-risk patients and the developed tools (care pathway and patient-specific report) each morning. Outcomes will be evaluated for a one-year period pre- and post-deployment. Primary outcome will be any vomiting within the 96-hour period post prediction time. Secondary outcomes will be the number of vomiting episodes within the 96-hour period, care pathway-consistent care, and specific antiemetic administrations.
The study team includes pediatric pharmacists, pediatric oncologists and experts in machine learning, clinical epidemiology, implementation sciences, care pathway development and biostatistics.
Vomiting is one of the most distressing aspects of cancer therapy and, with current approaches, medical management is failing a substantial number of patients. This work will contribute to precision medicine by identifying patients with the highest need for individualized review and therapy optimization. This effort is anticipated to improve the quality of care and quality of life for pediatric cancer patients.
Studientyp
Einschreibung (Tatsächlich)
Phase
- Unzutreffend
Kontakte und Standorte
Studienorte
-
-
Ontario
-
Toronto, Ontario, Kanada, M5G1X8
- The Hospital for Sick Children
-
-
Teilnahmekriterien
Zulassungskriterien
Studienberechtigtes Alter
- Kind
- Erwachsene
- Älterer Erwachsener
Akzeptiert gesunde Freiwillige
Studienberechtigte Geschlechter
Beschreibung
Inclusion Criteria:
- All pediatric patients admitted to the oncology service at SickKids
Exclusion Criteria:
- Pediatric patients admitted to the oncology service at SickKids that are discharged prior to prediction time
Studienplan
Wie ist die Studie aufgebaut?
Designdetails
- Hauptzweck: Unterstützende Pflege
- Zuteilung: N / A
- Interventionsmodell: Einzelgruppenzuweisung
- Maskierung: Keine (Offenes Etikett)
Waffen und Interventionen
Teilnehmergruppe / Arm |
Intervention / Behandlung |
|---|---|
|
Experimental: ML model
ML model to predict the risk of vomiting within the next 96 hours. |
For each patient, a ML model will predict the risk of vomiting within the next 96 hours. Patients will then receive care pathway-consistent interventions based on the ML model predictions.
Andere Namen:
|
Was misst die Studie?
Primäre Ergebnismessungen
Ergebnis Maßnahme |
Maßnahmenbeschreibung |
Zeitfenster |
|---|---|---|
|
Vomiting post prediction time
Zeitfenster: 0-96 hours post prediction time
|
The primary outcome will be any vomiting (a binary variable) 0-96 hours post prediction time. In the SickKids EHR, vomiting is described in the flowsheets by emesis volume, emesis count, emesis amount description, emesis color/appearance, and any vomiting/retching/gagging. Multiple descriptors can be used at a specific time stamp but no one descriptor is used consistently. Thus, the best measure of vomiting is a binary variable (yes/no) where yes represents any vomiting entry within the 96-hour window. Vomiting determination using this approach was validated. In a retrospective assessment, patients who received etoposide, ifosfamide or treosulfan were identified and 60 patients were randomly selected with stratification by age and HCT status. (Patel P et al, 2023) |
0-96 hours post prediction time
|
Sekundäre Ergebnismessungen
Ergebnis Maßnahme |
Maßnahmenbeschreibung |
Zeitfenster |
|---|---|---|
|
Number of episodes of vomiting
Zeitfenster: 0-96 hours post prediction time
|
The number of episodes of vomiting will be determined by counting the number of distinct time stamps with any vomiting description. |
0-96 hours post prediction time
|
|
Care pathway-consistent care
Zeitfenster: 0-96 hours post prediction time
|
Care pathway-consistent care will be measured as a binary outcome (yes/no). |
0-96 hours post prediction time
|
|
Specific antiemetic administrations
Zeitfenster: 0-96 hours post prediction time
|
Specific antiemetic administrations within the 96-hour window will be counted. |
0-96 hours post prediction time
|
Andere Ergebnismessungen
Ergebnis Maßnahme |
Maßnahmenbeschreibung |
Zeitfenster |
|---|---|---|
|
Number of Predictions and Interventions
Zeitfenster: 0-96 hours post prediction time
|
The number of times notes refer to the predictions and interventions to address them including antiemetic modifications during the prediction window will be descriptively reported. The role of the note writer will be documented (such as pharmacist or fellow). |
0-96 hours post prediction time
|
|
Number of times the prediction report dashboard was opened when a prediction was made.
Zeitfenster: 0-96 hour prediction window
|
The investigators will also describe the number of times the prediction report dashboard was opened when a prediction was made. |
0-96 hour prediction window
|
|
Nausea
Zeitfenster: 0-96 hour prediction window
|
Potential nausea events will be identified through automated retrieval of clinical notes containing nausea-related terms. Blinded research staff will subsequently review the notes and adjudicate whether nausea was present. |
0-96 hour prediction window
|
Mitarbeiter und Ermittler
Sponsor
Ermittler
- Hauptermittler: Lillian Sung, MD, PhD, The Hospital for Sick Children
- Hauptermittler: Lee Dupuis, RPh, PhD, The Hospital for Sick Children
- Hauptermittler: Priya Patel, PharmD, The Hospital for Sick Children
- Hauptermittler: Adam Yan, MD, MBI, The Hospital for Sick Children
- Hauptermittler: Lawrence Guo, PhD, The Hospital for Sick Children
Publikationen und hilfreiche Links
Studienaufzeichnungsdaten
Haupttermine studieren
Studienbeginn (Tatsächlich)
Primärer Abschluss (Tatsächlich)
Studienabschluss (Geschätzt)
Studienanmeldedaten
Zuerst eingereicht
Zuerst eingereicht, das die QC-Kriterien erfüllt hat
Zuerst gepostet (Tatsächlich)
Studienaufzeichnungsaktualisierungen
Letztes Update gepostet (Tatsächlich)
Letztes eingereichtes Update, das die QC-Kriterien erfüllt
Zuletzt verifiziert
Mehr Informationen
Begriffe im Zusammenhang mit dieser Studie
Schlüsselwörter
Zusätzliche relevante MeSH-Bedingungen
Andere Studien-ID-Nummern
- 3373
Plan für individuelle Teilnehmerdaten (IPD)
Planen Sie, individuelle Teilnehmerdaten (IPD) zu teilen?
Arzneimittel- und Geräteinformationen, Studienunterlagen
Studiert ein von der US-amerikanischen FDA reguliertes Arzneimittelprodukt
Studiert ein von der US-amerikanischen FDA reguliertes Geräteprodukt
Diese Informationen wurden ohne Änderungen direkt von der Website clinicaltrials.gov abgerufen. Wenn Sie Ihre Studiendaten ändern, entfernen oder aktualisieren möchten, wenden Sie sich bitte an register@clinicaltrials.gov. Sobald eine Änderung auf clinicaltrials.gov implementiert wird, wird diese automatisch auch auf unserer Website aktualisiert .